THE PERFORMANCE ANALYSIS OF TEMPLATE MATCHING SYSTEM IN LETTER IMAGE RECOGNITION USING ZONING FEATURE EXTRACTION AND INTEGRAL
PROJECTION FEATURE EXTRACTION Teofanus Dwiyanto N
1
M. Ilhamdi Rusydi, M.T.
2
Electrical Engineering Department, Engineering Faculty, Andalas University Email:
teofanusdwiyantongmail.com
1
, rilhamdiyahoo.com
2
Abstrack
Pattern recognition system has been widely applied in pattern recognition, especially the letters image. In letter pattern recognition, feature extraction process is also required to obtain characteristics
and specific feature of each image to be recognizable. There are various kinds of extraction of characteristics that can be used in the process of pattern recognition. In this research used two feature
extraction of zoning and integral projection.
In this study there are several stages of the process undertaken the design and implementation of systems for image object recognition alphabet capital letters A, I, U, E, O, B, C, D, F, G with a font style
Arial created with Microsoft Word and printed on paper. The first stage is capturing which is the process of taking pictures the image of the letter. The second stage is the conversion of RGB image of the letter to
the image intensity and image intensity will be segmented using bi-level luminance thresholding method. The next process is the labeling and filtering, followed by the process of feature extraction using zoning
and integral projection methods and the results of this extraction will be recognized by the template system matching. Tests conducted on 450 images obtained letters from the image of alphabet capital
letters A, I, U, E, O, B, C, D, F, G with font size 30, 40, 45, 50, 60, 65, 70, 80 , 85, 90, 100, 105, 110, 115, 120 and the distance between camera and letter image are 15 cm, 20 cm and 25 cm. In this study would
also analyze the performance of template matching system for each feature extraction of test data that has previously been used as a database system and the test data outside the database system.
Test results show that the template matching will work optimally if the data are used as test data, have previously been used as a database system and the system will work less than optimal if the data are
used as test data outside the database system. The percentage of the template matching recognition for testing with test data that has become a database system for each feature extraction is 100 and the
average percentage of template matching recognition for testing with test data outside the database system is 67.3 for couples zoning and template matching and 72.2 for couples integral projections
and template matching.
Key words: image, feature extraction, integral projection, template matching, zoning
1. Preface
12
Advances in information and technology are evolving so rapidly this century. And it all
happened against the backdrop of the human desire to go ahead and make human activities
more easily done. In doing everyday activities both personal activities and activities related to
the job, now it has been much aided by the results of technological advances and the
information itself. Thus, in some human
1
Student of Electrical Engineering Department Andalas University
2
Lecturer of Electrical Engineering Department Andalas University
activities need only punch a few buttons, or just out loud, then what he wants done by the tools
that became a substitute for hand, foot or mind. All of these developments can not be
separated from the tenacity of the scientists or scholars who continue to do research on science
and technology for the sake of efficiency of human activity.
Greatness wills of the computer at this time cannot be doubted. In the field of computer
vision has
also been
many significant
achievements obtained by the researchers. Computer vision is a term in a process that aims
F x,y
Sumber Cahaya Garis Normal
α
Permukaan objek
to make useful decisions about real physical objects and of a scene based on images obtained
from sensors such as cameras or the other. One
application of
technology development related to computer vision is how
an engine computer can recognize objects in images. Although object recognition is very easy
to do with human vision, but the automation of processing on the computer requires a variety of
image processing techniques to recognize an object. The human eye is a very complex visual
system. The recording process and the introduction of objects object recognition on
the human eye are in one system is intact, so that the human eye can immediately recognize and
define the object and background, as soon as eye shadow to capture and record an image. So, to
make a visual system of the machine based on the results of optical devices requiring prior
processing.
The objects recognition like these eyes inspired researchers to develop computer
applications for the automation of image processing to recognize objects. In realization of
this application takes at least an engine computer and camera as a sensor. The camera used to
capture images of objects in front of him. Computers are used as a machine that can
process data images from the camera and eventually recognize the image of the object in
front of him. Important stages in the process of image
recognition object,
namely the
introduction of object images off line by utilizing the characteristics or features of the
image object. Characteristics of image-objects in the input is used as a comparison with the
characteristics of the object image stored on a database so that the process can recognize any
pictures of objects that are input by the user. The process of comparison features of object images
that are input with the features images of objects that exist in the database named by the template
matching process.
Based on the thinking and research above, the authors are interested to implementing it
with compare between the two feature extraction that is focused on the letters of the alphabet
capital letter with image acquisition using a camera and using a template matching as a
pattern recognition technique. This process is structured in the final task of the study, entitled
“The Performance Analysis of Template Matching System in Letter Image Recognition
Using Zoning Feature Extraction and Integral Projection Feature Extraction.
2. Literature Review 2.1. Image Formation
